CtrlK
BlogDocsLog inGet started
Tessl Logo

miro-code-explain-on-board

Use when the user wants to explain or visualize a codebase on a Miro board — produces a minimal, notation-correct set of architecture / structure / behavior diagrams (flowchart, UML class, UML sequence, ERD) plus a short companion document, grounded in real repo artifacts.

72

Quality

88%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

85%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A well-engineered instruction-only skill: a clearly sequenced workflow with mandatory checks and feedback loops, appropriate progressive disclosure to a verified one-level-deep reference, and highly concrete operational details. Its only real costs are duplicated rule statements and the absence of any worked example inline.

Suggestions

De-duplicate rules stated twice: the banned-verb list and the flowchart shape rules appear in both 'Core diagramming principles' and the step 4/5 checks — state each once and cross-reference (e.g. 're-run the edge-label check from the principles section').

Add one compact worked example — a single sample plan entry (id, title, question, notation, edge semantics) — so the plan format is copy-paste concrete rather than only field-described.

Trim step 6 layout detail slightly (the 1600x900 pitch sentence overlaps what the loaded composer guidance already states) to cut tokens without losing actionability.

DimensionReasoningScore

Conciseness

The body is dense, imperative, and free of concept re-teaching, but the banned-verb list and the shape rules are each stated twice (Core diagramming principles and again in steps 4–5), so it is efficient with minor trimmable repetition — anchor 4, not 3 (no padded explanation) and not 5 (every token does not quite earn its place).

4 / 5

Actionability

Guidance is highly concrete (exact widget data-types, the 1600x900 layout pitch, XML-escaping rules, plan fields, update-vs-regenerate semantics), but no worked example (a sample plan entry or Mermaid fragment) appears inline; the explicit deferral of format mechanics to runtime-loaded guidance is a justified flexibility, placing this at anchor 4 rather than 5 or 3.

4 / 5

Workflow Clarity

Steps 0–7 are clearly sequenced with explicit validation checkpoints: MANDATORY pre-compilation checks, a final shape audit, and a reflow feedback loop that iterates from the latest result_svg until spacing is clean, plus explicit error reporting ("if a diagram fails, report the error with the offending Mermaid as-is") — matching the 5 anchor.

5 / 5

Progressive Disclosure

The SKILL.md is a well-organized overview that inlines only the essentials and pushes the full R1–R9/H1–H4 ruleset to references/diagramming-principles.md (verified to exist, one level deep, clearly signaled in the References section), matching the 5 anchor.

5 / 5

Total

18

/

20

Passed

Description

92%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong description: third person, concise, with an explicit 'Use when…' trigger and a concrete, enumerated account of what the skill produces. The only weakness is slightly narrow trigger vocabulary.

DimensionReasoningScore

Specificity

"produces a minimal, notation-correct set of architecture / structure / behavior diagrams (flowchart, UML class, UML sequence, ERD) plus a short companion document, grounded in real repo artifacts" lists multiple specific concrete actions with comprehensive coverage, matching the 5 anchor rather than the 4 anchor (which allows minor coverage gaps).

5 / 5

Completeness

It explicitly answers both: "Use when the user wants to explain or visualize a codebase on a Miro board" (when, with concrete trigger phrases) and the full production scope (what), matching the 5 anchor exactly.

5 / 5

Trigger Term Quality

Natural phrases like "explain or visualize a codebase", "Miro board", and "architecture" are present, but a few common variations users might say (e.g. "draw", "diagram the system", "whiteboard") are missing — good coverage, not comprehensive, so 4 rather than 5, and clearly above 3.

4 / 5

Distinctiveness Conflict Risk

The Miro-board target plus codebase-explanation purpose carves a clear niche with distinct triggers and minimal overlap risk with generic diagramming or code-explanation skills, matching the 5 anchor.

5 / 5

Total

19

/

20

Passed

Validation

100%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
miroapp/miro-ai
Reviewed

Table of Contents

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.